6results about How to "Reliable input" patented technology

The application provides an engine active clearance design method, and belongs to the technical field of aero-engines. The method comprises the following steps: constructing a rigid-flexible coupling finite element model coupled with multi-body dynamics and finite elements; solving deformation under gyroscopic effect and inertial load and deformation under thermal coupling effect when the engine is in use; extracting clearance deformation between a rotating rotor and a rotating stator and clearance deformation between a rotating rotor and a stationary stator based on the solving of the deformation; identifying a deformation sensitive area; performing multi-objective optimization on the structure of the deformation sensitive area; based on the optimized result, and considering other factors that have an influence on the clearance between the rotor and the stator, designing an initial installation clearance value that takes into account safety and efficiency, wherein the other factors include radial movement of bearing and fulcrum elastic elements, rotor and stator runout, and relative axial position change of the rotor and the stator. Through the processing scheme, the accuracy of the active clearance design is improved, the safety and efficiency of the engine are taken into account, and the risk of engine collision and abrasion is reduced.

The application belongs to the technical field of intelligent breeding, and provides a sow leg automatic scoring method and device based on three-dimensional point cloud. The method comprises the following steps: acquiring a target three-dimensional point cloud model of a pig; extracting a leg point cloud set corresponding to each leg of the pig from the target three-dimensional point cloud model; determining leg key point data of each leg from the leg point cloud set corresponding to each leg; determining trunk key point data from the target three-dimensional point cloud model according to the leg key point data; determining a posture determination result of the pig according to the target three-dimensional point cloud model, the leg key point data of each leg and the trunk key point data; and in the case that the posture determination result indicates that the pig is in a standard standing posture, determining a leg structure type and a leg structure score of the pig according to the leg key point data. The application can stably identify the leg structure characteristics of the pig and realize consistent automatic scoring, and has good application potential in terms of accuracy, robustness and interpretability.

This application discloses a hierarchical adaptive intelligent association and alignment method for multimodal flight data, comprising: acquiring multi-source airborne flight data and preprocessing it; mapping data of different modes in the preprocessed multi-source airborne flight data to a common feature space to obtain cross-modal alignment features, wherein an aircraft physical dynamic model is introduced as a constraint during the mapping process; performing local precise association and global semantic association in parallel based on the cross-modal alignment features; wherein the local precise association is used to obtain pixel-level or point-level matching results, and the global semantic association is used to obtain globally consistent semantic association results; and fusing the results of the local precise association and the global semantic association to obtain association information of corresponding granularity. This invention effectively solves the "data silo" problem caused by differences in format, spatiotemporal reference, and modality of multi-source flight data, significantly improving association accuracy, robustness, and system adaptability.

This invention relates to the field of power system monitoring and data analysis technology, and discloses a method for accurate identification and load separation of charging users without individual charging records. The method includes: acquiring electricity load data of users within a target area; extracting at least two different dimensions of electricity consumption characteristics based on the electricity load data; constructing a hierarchical identification model to perform hierarchical progressive analysis and verification of the at least two different dimensions of electricity consumption characteristics according to a preset logic, so as to identify charging users from those without independent charging metering records; and performing decoupling analysis on the associated total electricity load data based on the identified charging user information to separate the charging load. This invention introduces a dynamic calibration mechanism based on seasons and holidays, enabling the identification and separation model to adapt to load characteristic changes at different time scales, ensuring the accuracy and stability of long-term applications.

The invention discloses a surface mine unmanned road adhesion coefficient estimation method, which comprises the following steps of S1, extracting a plurality of characteristic factors related to a road adhesion coefficient from a historical operation data set of an unmanned mine car to form an original characteristic data set; s2, performing data cleaning on the original feature data set, dividing the original feature data set into a training set and a test set, and performing standardization processing; s3, performing noise detection and elimination on the standardized training set and the test set based on an isolated forest algorithm to obtain a denoised training set and a denoised test set; s4, training a recurrent neural network model by using the denoised training set to obtain a trained road adhesion coefficient estimation model; and inputting the denoised test set into the road adhesion coefficient estimation model to obtain a road adhesion coefficient estimation value. And high-precision and strong-adaptive real-time estimation of the pavement adhesion coefficient in the unstructured and steep-gradient pavement environment of the surface mine is realized.

This invention discloses a self-supervised learning prediction method and system for spatiotemporal meteorological-power data, primarily applied to the field of new energy power generation prediction. The method first acquires historical power, historical meteorological data, and future meteorological forecast data from wind farms, performing spatiotemporal interpolation for completion, 3σ outlier removal, Min-Max normalization, and spatial grid alignment preprocessing. Then, it constructs a meteorological-power pre-training framework based on physical simulation, incorporating time-series frequency alignment prediction. This framework includes a core model pre-trained using virtual wind farm data, a time-series alignment network, an adaptive multi-scale spatiotemporal fusion module, and a dual-branch feature extraction network. Next, a self-supervised calibration gated fusion module dynamically fuses spatiotemporal and temporal features. Finally, labeled data is used to fine-tune the complete model and optimize parameters. The system then outputs ultra-short-term and medium-short-term wind power predictions based on the input data. This invention significantly improves prediction accuracy and generalization ability, providing reliable support for power system dispatching.